trsdimi's picture
First version
0f414c4 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5501410961151123,
"min": 0.5235671401023865,
"max": 1.4480878114700317,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16521.837890625,
"min": 15572.98046875,
"max": 43929.19140625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989978.0,
"min": 29994.0,
"max": 989978.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989978.0,
"min": 29994.0,
"max": 989978.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4602265954017639,
"min": -0.12661336362361908,
"max": 0.4849260747432709,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 126.56231689453125,
"min": -30.51382064819336,
"max": 130.93003845214844,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.024532079696655273,
"min": -0.024532079696655273,
"max": 0.539347231388092,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -6.746321678161621,
"min": -6.746321678161621,
"max": 128.90399169921875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06714202910007881,
"min": 0.06511485770058173,
"max": 0.07467493486581082,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9399884074011033,
"min": 0.5755093432623684,
"max": 1.0639837811759207,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01639168887416237,
"min": 0.0006671252535927399,
"max": 0.016455964878615406,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22948364423827317,
"min": 0.008672628296705618,
"max": 0.24683947317923108,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.300426137985715e-06,
"min": 7.300426137985715e-06,
"max": 0.0002949247891917375,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010220596593180001,
"min": 0.00010220596593180001,
"max": 0.003632250189249999,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243344285714286,
"min": 0.10243344285714286,
"max": 0.1983082625,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340682,
"min": 1.4340682,
"max": 2.6107500000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002531009414285715,
"min": 0.0002531009414285715,
"max": 0.009830995423749999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003543413180000001,
"min": 0.003543413180000001,
"max": 0.12109392500000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014331070706248283,
"min": 0.014331070706248283,
"max": 0.5498520731925964,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20063498616218567,
"min": 0.20063498616218567,
"max": 4.3988165855407715,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 398.6164383561644,
"min": 374.5,
"max": 996.0645161290323,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29099.0,
"min": 17687.0,
"max": 34511.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4369424418227312,
"min": -0.9323806957371773,
"max": 1.5557999710895514,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 104.89679825305939,
"min": -29.763601697981358,
"max": 120.60879875719547,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4369424418227312,
"min": -0.9323806957371773,
"max": 1.5557999710895514,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 104.89679825305939,
"min": -29.763601697981358,
"max": 120.60879875719547,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05954046686244124,
"min": 0.05806652917715091,
"max": 10.437240360598816,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.34645408095821,
"min": 4.34645408095821,
"max": 198.3075668513775,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1712410340",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712412746"
},
"total": 2406.037608825,
"count": 1,
"self": 1.0508580150003581,
"children": {
"run_training.setup": {
"total": 0.0619756309999957,
"count": 1,
"self": 0.0619756309999957
},
"TrainerController.start_learning": {
"total": 2404.924775179,
"count": 1,
"self": 1.554672865005159,
"children": {
"TrainerController._reset_env": {
"total": 2.9675668370000494,
"count": 1,
"self": 2.9675668370000494
},
"TrainerController.advance": {
"total": 2400.2529841659943,
"count": 63702,
"self": 1.6759649600453486,
"children": {
"env_step": {
"total": 1739.301318761975,
"count": 63702,
"self": 1590.7581247959515,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.5593162809564,
"count": 63702,
"self": 5.327452440938487,
"children": {
"TorchPolicy.evaluate": {
"total": 142.23186384001792,
"count": 62547,
"self": 142.23186384001792
}
}
},
"workers": {
"total": 0.9838776850670001,
"count": 63702,
"self": 0.0,
"children": {
"worker_root": {
"total": 2399.1874263350073,
"count": 63702,
"is_parallel": true,
"self": 944.97210573403,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006073057999969933,
"count": 1,
"is_parallel": true,
"self": 0.004374962000156302,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016980959998136314,
"count": 8,
"is_parallel": true,
"self": 0.0016980959998136314
}
}
},
"UnityEnvironment.step": {
"total": 0.053844074000039654,
"count": 1,
"is_parallel": true,
"self": 0.0006847820001212312,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005176999999321197,
"count": 1,
"is_parallel": true,
"self": 0.0005176999999321197
},
"communicator.exchange": {
"total": 0.05092156399996384,
"count": 1,
"is_parallel": true,
"self": 0.05092156399996384
},
"steps_from_proto": {
"total": 0.0017200280000224666,
"count": 1,
"is_parallel": true,
"self": 0.0003996469999947294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013203810000277372,
"count": 8,
"is_parallel": true,
"self": 0.0013203810000277372
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1454.2153206009773,
"count": 63701,
"is_parallel": true,
"self": 37.703494246015225,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.26946661295551,
"count": 63701,
"is_parallel": true,
"self": 26.26946661295551
},
"communicator.exchange": {
"total": 1278.1362599159925,
"count": 63701,
"is_parallel": true,
"self": 1278.1362599159925
},
"steps_from_proto": {
"total": 112.10609982601409,
"count": 63701,
"is_parallel": true,
"self": 23.575730148027105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.53036967798698,
"count": 509608,
"is_parallel": true,
"self": 88.53036967798698
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 659.275700443974,
"count": 63702,
"self": 3.0709444690131704,
"children": {
"process_trajectory": {
"total": 137.72291646996393,
"count": 63702,
"self": 137.40428634896386,
"children": {
"RLTrainer._checkpoint": {
"total": 0.31863012100006927,
"count": 2,
"self": 0.31863012100006927
}
}
},
"_update_policy": {
"total": 518.4818395049969,
"count": 459,
"self": 304.7044461120114,
"children": {
"TorchPPOOptimizer.update": {
"total": 213.77739339298546,
"count": 22758,
"self": 213.77739339298546
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3330000001587905e-06,
"count": 1,
"self": 1.3330000001587905e-06
},
"TrainerController._save_models": {
"total": 0.14954997800032288,
"count": 1,
"self": 0.002304514000115887,
"children": {
"RLTrainer._checkpoint": {
"total": 0.147245464000207,
"count": 1,
"self": 0.147245464000207
}
}
}
}
}
}
}